INDEX

Explanations

attributes of architectural features and decorations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chet

-0.16

orgia

-0.16

å´İ

-0.15

odial

-0.15

 sublist

-0.15

eshire

-0.14

Ð½ÐµÑģ

-0.14

ÑĨÐ²ÐµÑĤ

-0.14

 fiction

-0.13

ouri

-0.13

POSITIVE LOGITS

 ceiling

0.57

 ceilings

0.55

 Ceiling

0.50

 Ð¿Ð¾ÑĤÐ¾Ð»

0.44

 roof

0.37

 overhead

0.37

 ceil

0.35

ceil

0.35

 vault

0.34

-ce

0.33

Activations Density 0.106%

attributes of architectural features and decorations

No Comments

No Known Activations